Files
dierk 3ef43019be Add in-DB indexing script, benchmark results, schema names in presentation
- index_images_indb.py: new script indexing via VECTOR_EMBEDDING(CLIP_IMG)
  using a two-step INSERT+UPDATE to work around ORA-24816
- index_images_oracle.py / index_images.py: add timing output
- Presentation: schema names VECTORS_USER/VECTOR in diagram and comparison,
  ONNX expansion, HNSW index note on slide 11,
  indexing times updated from 3-run benchmark (avg: PG 12.1s, Ora 12.1s, InDB 13.6s)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-20 10:42:13 +02:00

70 lines
2.0 KiB
Python

import os
import array
import time
from dotenv import load_dotenv
from db_oracle import get_connection
from embedder import embed_image
load_dotenv()
PHOTOS_DIR = os.getenv("PHOTOS_DIR")
CREATE_TABLE = """
CREATE TABLE images (
id NUMBER GENERATED ALWAYS AS IDENTITY PRIMARY KEY,
filename VARCHAR2(255) NOT NULL UNIQUE,
filepath VARCHAR2(1000) NOT NULL,
embedding VECTOR(512, FLOAT32)
)
"""
CREATE_INDEX = """
CREATE VECTOR INDEX images_embedding_idx
ON images(embedding)
ORGANIZATION INMEMORY NEIGHBOR GRAPH
WITH DISTANCE COSINE
WITH TARGET ACCURACY 95
PARAMETERS (type HNSW, neighbors 32, efconstruction 200)
"""
INSERT = "INSERT INTO images (filename, filepath, embedding) VALUES (:1, :2, :3)"
def table_exists(cur):
cur.execute("SELECT COUNT(*) FROM user_tables WHERE table_name = 'IMAGES'")
return cur.fetchone()[0] > 0
def main():
conn = get_connection()
cur = conn.cursor()
if not table_exists(cur):
cur.execute(CREATE_TABLE)
cur.execute(CREATE_INDEX)
conn.commit()
print("Table and index created.")
else:
print("Table already exists, skipping creation.")
files = [f for f in os.listdir(PHOTOS_DIR) if f.lower().endswith((".jpg", ".jpeg"))]
print(f"Found {len(files)} photos in {PHOTOS_DIR}")
start = time.time()
for i, filename in enumerate(files, 1):
filepath = os.path.join(PHOTOS_DIR, filename)
cur.execute("SELECT 1 FROM images WHERE filename = :1", (filename,))
if cur.fetchone():
print(f"[{i}/{len(files)}] Skipping {filename} (already indexed)")
continue
# oracledb requires array.array("f") for VECTOR(512, FLOAT32) — plain list is rejected.
embedding = array.array("f", embed_image(filepath))
cur.execute(INSERT, (filename, filepath, embedding))
conn.commit()
print(f"[{i}/{len(files)}] Indexed {filename}")
cur.close()
conn.close()
print(f"Done in {time.time() - start:.1f} seconds.")
if __name__ == "__main__":
main()